1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
|
// SPDX-License-Identifier: GPL-2.0
// Copyright (C) 2005-2017 Andes Technology Corporation
#include <linux/extable.h>
#include <linux/module.h>
#include <linux/signal.h>
#include <linux/ptrace.h>
#include <linux/mm.h>
#include <linux/init.h>
#include <linux/hardirq.h>
#include <linux/uaccess.h>
#include <asm/pgtable.h>
#include <asm/tlbflush.h>
extern void die(const char *str, struct pt_regs *regs, long err);
/*
* This is useful to dump out the page tables associated with
* 'addr' in mm 'mm'.
*/
void show_pte(struct mm_struct *mm, unsigned long addr)
{
pgd_t *pgd;
if (!mm)
mm = &init_mm;
pr_alert("pgd = %p\n", mm->pgd);
pgd = pgd_offset(mm, addr);
pr_alert("[%08lx] *pgd=%08lx", addr, pgd_val(*pgd));
do {
pmd_t *pmd;
if (pgd_none(*pgd))
break;
if (pgd_bad(*pgd)) {
pr_alert("(bad)");
break;
}
pmd = pmd_offset(pgd, addr);
#if PTRS_PER_PMD != 1
pr_alert(", *pmd=%08lx", pmd_val(*pmd));
#endif
if (pmd_none(*pmd))
break;
if (pmd_bad(*pmd)) {
pr_alert("(bad)");
break;
}
if (IS_ENABLED(CONFIG_HIGHMEM))
{
pte_t *pte;
/* We must not map this if we have highmem enabled */
pte = pte_offset_map(pmd, addr);
pr_alert(", *pte=%08lx", pte_val(*pte));
pte_unmap(pte);
}
} while (0);
pr_alert("\n");
}
void do_page_fault(unsigned long entry, unsigned long addr,
unsigned int error_code, struct pt_regs *regs)
{
struct task_struct *tsk;
struct mm_struct *mm;
struct vm_area_struct *vma;
siginfo_t info;
int fault;
unsigned int mask = VM_READ | VM_WRITE | VM_EXEC;
unsigned int flags = FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE;
error_code = error_code & (ITYPE_mskINST | ITYPE_mskETYPE);
tsk = current;
mm = tsk->mm;
info.si_code = SEGV_MAPERR;
/*
* We fault-in kernel-space virtual memory on-demand. The
* 'reference' page table is init_mm.pgd.
*
* NOTE! We MUST NOT take any locks for this case. We may
* be in an interrupt or a critical region, and should
* only copy the information from the master page table,
* nothing more.
*/
if (addr >= TASK_SIZE) {
if (user_mode(regs))
goto bad_area_nosemaphore;
if (addr >= TASK_SIZE && addr < VMALLOC_END
&& (entry == ENTRY_PTE_NOT_PRESENT))
goto vmalloc_fault;
else
goto no_context;
}
/* Send a signal to the task for handling the unalignment access. */
if (entry == ENTRY_GENERAL_EXCPETION
&& error_code == ETYPE_ALIGNMENT_CHECK) {
if (user_mode(regs))
goto bad_area_nosemaphore;
else
goto no_context;
}
/*
* If we're in an interrupt or have no user
* context, we must not take the fault..
*/
if (unlikely(faulthandler_disabled() || !mm))
goto no_context;
/*
* As per x86, we may deadlock here. However, since the kernel only
* validly references user space from well defined areas of the code,
* we can bug out early if this is from code which shouldn't.
*/
if (unlikely(!down_read_trylock(&mm->mmap_sem))) {
if (!user_mode(regs) &&
!search_exception_tables(instruction_pointer(regs)))
goto no_context;
retry:
down_read(&mm->mmap_sem);
} else {
/*
* The above down_read_trylock() might have succeeded in which
* case, we'll have missed the might_sleep() from down_read().
*/
might_sleep();
if (IS_ENABLED(CONFIG_DEBUG_VM)) {
if (!user_mode(regs) &&
!search_exception_tables(instruction_pointer(regs)))
goto no_context;
}
}
vma = find_vma(mm, addr);
if (unlikely(!vma))
goto bad_area;
if (vma->vm_start <= addr)
goto good_area;
if (unlikely(!(vma->vm_flags & VM_GROWSDOWN)))
goto bad_area;
if (unlikely(expand_stack(vma, addr)))
goto bad_area;
/*
* Ok, we have a good vm_area for this memory access, so
* we can handle it..
*/
good_area:
info.si_code = SEGV_ACCERR;
/* first do some preliminary protection checks */
if (entry == ENTRY_PTE_NOT_PRESENT) {
if (error_code & ITYPE_mskINST)
mask = VM_EXEC;
else {
mask = VM_READ | VM_WRITE;
if (vma->vm_flags & VM_WRITE)
flags |= FAULT_FLAG_WRITE;
}
} else if (entry == ENTRY_TLB_MISC) {
switch (error_code & ITYPE_mskETYPE) {
case RD_PROT:
mask = VM_READ;
break;
case WRT_PROT:
mask = VM_WRITE;
flags |= FAULT_FLAG_WRITE;
break;
case NOEXEC:
mask = VM_EXEC;
break;
case PAGE_MODIFY:
mask = VM_WRITE;
flags |= FAULT_FLAG_WRITE;
break;
case ACC_BIT:
BUG();
default:
break;
}
}
if (!(vma->vm_flags & mask))
goto bad_area;
/*
* If for any reason at all we couldn't handle the fault,
* make sure we exit gracefully rather than endlessly redo
* the fault.
*/
fault = handle_mm_fault(vma, addr, flags);
/*
* If we need to retry but a fatal signal is pending, handle the
* signal first. We do not need to release the mmap_sem because it
* would already be released in __lock_page_or_retry in mm/filemap.c.
*/
if ((fault & VM_FAULT_RETRY) && fatal_signal_pending(current)) {
if (!user_mode(regs))
goto no_context;
return;
}
if (unlikely(fault & VM_FAULT_ERROR)) {
if (fault & VM_FAULT_OOM)
goto out_of_memory;
else if (fault & VM_FAULT_SIGBUS)
goto do_sigbus;
else
goto bad_area;
}
/*
* Major/minor page fault accounting is only done on the initial
* attempt. If we go through a retry, it is extremely likely that the
* page will be found in page cache at that point.
*/
if (flags & FAULT_FLAG_ALLOW_RETRY) {
if (fault & VM_FAULT_MAJOR)
tsk->maj_flt++;
else
tsk->min_flt++;
if (fault & VM_FAULT_RETRY) {
flags &= ~FAULT_FLAG_ALLOW_RETRY;
flags |= FAULT_FLAG_TRIED;
/* No need to up_read(&mm->mmap_sem) as we would
* have already released it in __lock_page_or_retry
* in mm/filemap.c.
*/
goto retry;
}
}
up_read(&mm->mmap_sem);
return;
/*
* Something tried to access memory that isn't in our memory map..
* Fix it, but check if it's kernel or user first..
*/
bad_area:
up_read(&mm->mmap_sem);
bad_area_nosemaphore:
/* User mode accesses just cause a SIGSEGV */
if (user_mode(regs)) {
tsk->thread.address = addr;
tsk->thread.error_code = error_code;
tsk->thread.trap_no = entry;
info.si_signo = SIGSEGV;
info.si_errno = 0;
/* info.si_code has been set above */
info.si_addr = (void *)addr;
force_sig_info(SIGSEGV, &info, tsk);
return;
}
no_context:
/* Are we prepared to handle this kernel fault?
*
* (The kernel has valid exception-points in the source
* when it acesses user-memory. When it fails in one
* of those points, we find it in a table and do a jump
* to some fixup code that loads an appropriate error
* code)
*/
{
const struct exception_table_entry *entry;
if ((entry =
search_exception_tables(instruction_pointer(regs))) !=
NULL) {
/* Adjust the instruction pointer in the stackframe */
instruction_pointer(regs) = entry->fixup;
return;
}
}
/*
* Oops. The kernel tried to access some bad page. We'll have to
* terminate things with extreme prejudice.
*/
bust_spinlocks(1);
pr_alert("Unable to handle kernel %s at virtual address %08lx\n",
(addr < PAGE_SIZE) ? "NULL pointer dereference" :
"paging request", addr);
show_pte(mm, addr);
die("Oops", regs, error_code);
bust_spinlocks(0);
do_exit(SIGKILL);
return;
/*
* We ran out of memory, or some other thing happened to us that made
* us unable to handle the page fault gracefully.
*/
out_of_memory:
up_read(&mm->mmap_sem);
if (!user_mode(regs))
goto no_context;
pagefault_out_of_memory();
return;
do_sigbus:
up_read(&mm->mmap_sem);
/* Kernel mode? Handle exceptions or die */
if (!
|